Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover the safe read-only, idempotent profile, yet the description adds substantive behavior: the counting rule (a proposal counts only if a label, PR text, title, or proposal file names the RFP), the fact that most proposals do not, and the caution that a low count is not proof of an uncrowded area. It also describes what a full read of one RFP returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and returned fields, then layered with usage routing and the counting caveat. Dense but largely earned; the numbering example and the uncrowded-area warning are the only mildly expendable lines, and both carry real interpretive value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does so for both modes (list vs. single-RFP read). It also supplies domain scoping ('Canton-specific') and the counting semantics an agent needs to interpret results correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single parameter is already documented, so the baseline is 3. The description adds meaning beyond the schema: what passing `number` actually yields (what the Foundation asks for, grant appetite, prior funded examples, declaring proposals) and the RFP numbering convention ('RFP 18 is Integration into SDLCs').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('List the Canton Foundation Dev Fund Requests for Proposals') plus the exact fields returned (number, title, category, declaration count). It also contrasts itself with the sibling find_rfp_for_idea, so an agent can distinguish the enumeration tool from the matching tool without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Routes the agent explicitly: use find_rfp_for_idea to find the RFP that fits an idea, and pass `number` here to read one RFP in full. It also warns how to interpret low counts. There is no explicit when-not-to-use statement, but the alternative and its triggering condition are named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.